Analysis of DNAs associated with coconut foliar decay disease implicates a unique single-stranded DNA virus representing a new taxon

Abstract

The unique ecology, pathology and undefined taxonomy of coconut foliar decay virus (CFDV), found associated with coconut foliar decay disease (CFD) in 1986, prompted analyses of old virus samples by modern methods. Rolling circle amplification and deep sequencing applied to nucleic acid extracts from virion preparations and CFD-affected palms identified twelve distinct circular DNAs, eleven of which had a size of about 1.3 kb and one of 641 nt. Mass spectrometry-based protein identification proved that a 24 kDa protein encoded by two 1.3 kb DNAs is the virus capsid protein with highest sequence similarity to that of grabloviruses (family Geminiviridae), even though CFDV particles are not geminate. The nine other 1.3 kb DNAs represent alphasatellites coding for replication initiator proteins that differ clearly from those encoded by nanovirid DNA-R. The 641 nt DNA-gamma is unique and may encode a movement protein. Three DNAs, alphasatellite CFDAR, capsid protein encoding CFDV DNA-S.1 and DNA-gamma share sequence motifs near their replication origins and were consistently present in all samples analysed. These DNAs appear to be integral components of a possibly tripartite CFDV genome, different from those of any Geminiviridae or Nanoviridae family member, implicating CFDV as representative of a new genus and family.

Figure 1

Identification of the CFDV capsid protein. (a) SDS-PAGE showing that CFDV has a capsid protein of Mr ~24 kDa as estimated using (lane 1) tobacco mosaic virus capsid protein (18 kDa), (lane 2) carbonic anhydrase (29 kDa) and (lane 3) cytochrome c (12 kDa) as size markers. (b) Comparison of CFDV CP1, encoded by CFDV [VU;89] DNA-S.1, with a capsid protein of a grablovirus, here GRBV protein AGV40193. Identical amino acids are displayed in red and marked by (|), similar amino acids are marked by (+). Tryptic peptides of CFDV particle-derived capsid protein, identified by mass spectrometry, are shown at matching positions below the protein sequence of CFDV CP1.

Figure 2

Maximum likelihood phylogenetic tree of selected alphasatellite DNAs and pairwise sequence identity plot. Apart from all coconut foliar decay alphasatellites only representatives of the most distantly related alphasatellites were chosen for comparison. (a) The PhyML tree was rooted using the BBTV DNA-R sequence (S56276). Branch support (% bootstrap) is indicated. Nodes with <70% bootstrap support were collapsed. Branches are coloured according to clustering of the alphasatellites. Red: coconut foliar decay alphasatellites; orange: babuvirus alphasatellites (incl. CFDA3 and CFDA6); brown, ochre, green: alphasatellites associated with begomoviruses and those isolated from insects; olive, violet, blue: nanovirus-associated alphasatellites. Names are according to and GenBank accession numbers are indicated. (b) A pairwise DNA sequence comparison plot by SDT with % identity shown as a multicolour heat map.

Figure 3

Comparison of replication origin sequences of 12 DNAs found associated with CFD disease. The origin sequences of components (indicated on the left) are aligned. Inverted repeat sequences (horizontal arrows) potentially forming a stem-loop (STL) are boxed. The vertical arrow indicates the position of potential cleavage by Rep protein. Conserved sequences shared by DNA-S.1, DNA-S.2 and some alphasatellites, are indicated by small boxes. The pentanucleotide AGCGT at the 5′ end of the stem-loop and its respective complement at the 3′ end shared by DNA-S.1 and CFDAR is indicated by an open-headed arrow, and the potential iteron sequence TGCT is indicated by an arrow. Potential TATA-box sequences at 5′ of the STL region are in bold; ATG start codons of rep genes, if within the borders of the alignments, are in bold and underlined; potential TATA-box sequences at the 3′ of the STL region are in italics. Gamma (+) and gamma (−) are two potential origin sequences that occur at different positions of the plus or the complementary strand of CFDV DNA-gamma.

Figure 4

Symptoms of coconut foliar decay disease and genetic organisation of circular DNAs found associated with it. The identified DNAs are grouped according to their phylogenetic relationships. The presumed integral genome components DNA-S.1, DNA-gamma and alphasatellite R are shown next to each other. Inside each circle the name of the respective DNA is given. Shared potential open reading frames (ORFs) are indicated by the arrows of the same colours: red for the ORF encoding Rep (replication initiator protein); green for CP (capsid protein); brown for CFDAR_ORF2, CFDA1_ORF2, CFDA2_ORF2, CFDA4_ORF2, CFDA5_ORF2, CFDA8_ORF2; pink for CFDA2_ORF4 and CFDA5_ORF4, blue for CFDA2_ORF3, CFDA4_ORF4, CFDA5_ORF3 and CFDA8_ORF3. All other ORFs shown in different colours (orange, light-brown, grey, lime-green, purple, violet and black) are unique. SL – potential stem loop (inverted repeat sequences flanking the replication origin), symbolized by a knob; an empty knob represents the potential stem loop on the complementary (−) strand of CFDV DNA-gamma; CR-SL - common region around the stem loop region. Where TATA boxes could be associated with ORFs the colours of their indicative asterisks match those of the ORFs. In the centre, the CFD-affected MRD palm from which the 2015 sample originated is shown.

Figure 5

Alignment of amino acid sequences of movement proteins of several ssDNA viruses and luteoviruses. Alignments were done using ClustalW in MegAlign of DNASTAR. Names and accession numbers of the movement proteins of selected babuviruses (a), mastreviruses (b), nanoviruses (c) and luteoviruses (d) are indicated on the left. Potential movement protein ‘signature’ – stretches of hydrophobic amino acids as well as of basic (R, K) and acidic (D, E) side chains are boxed. The similarity of amino acid stretches of the potential ORF 1 protein of CFDV DNA-gamma is highest with the movement proteins of babuviruses.